Duplicate from valentinafeve/yolos-fashionpedia

Co-authored-by: Valentina Feruere <valentinafeve@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,23 @@
+---
+datasets:
+- detection-datasets/fashionpedia
+language:
+- en
+pipeline_tag: object-detection
+tags:
+- YOLOS
+- Object detection
+---
+
+This is a fine-tunned object detection model for fashion.
+
+For more details of the implementation you can check the source code [here](https://github.com/valntinaf/fine_tunning_YOLOS_for_fashion)
+
+the dataset used for its training is available [here](https://huggingface.co/datasets/detection-datasets/fashionpedia)
+
+this model supports the following categories:
+
+CATS = ['shirt, blouse', 'top, t-shirt, sweatshirt', 'sweater', 'cardigan', 'jacket', 'vest', 'pants', 'shorts', 'skirt', 'coat', 'dress', 'jumpsuit', 'cape', 'glasses', 'hat', 'headband, head covering, hair accessory', 'tie', 'glove', 'watch', 'belt', 'leg warmer', 'tights, stockings', 'sock', 'shoe', 'bag, wallet', 'scarf', 'umbrella', 'hood', 'collar', 'lapel', 'epaulette', 'sleeve', 'pocket', 'neckline', 'buckle', 'zipper', 'applique', 'bead', 'bow', 'flower', 'fringe', 'ribbon', 'rivet', 'ruffle', 'sequin', 'tassel']
+
+
+![image](https://miro.medium.com/v2/resize:fit:1400/format:webp/1*q8TTgxX_gf6vRe5AJN2r4g.png)

config.json

@@ -0,0 +1,130 @@
+{
+  "_name_or_path": "valentinafeve/yolos-fashionpedia",
+  "architectures": [
+    "YolosForObjectDetection"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_loss": false,
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "shirt, blouse",
+    "1": "top, t-shirt, sweatshirt",
+    "2": "sweater",
+    "3": "cardigan",
+    "4": "jacket",
+    "5": "vest",
+    "6": "pants",
+    "7": "shorts",
+    "8": "skirt",
+    "9": "coat",
+    "10": "dress",
+    "11": "jumpsuit",
+    "12": "cape",
+    "13": "glasses",
+    "14": "hat",
+    "15": "headband, head covering, hair accessory",
+    "16": "tie",
+    "17": "glove",
+    "18": "watch",
+    "19": "belt",
+    "20": "leg warmer",
+    "21": "tights, stockings",
+    "22": "sock",
+    "23": "shoe",
+    "24": "bag, wallet",
+    "25": "scarf",
+    "26": "umbrella",
+    "27": "hood",
+    "28": "collar",
+    "29": "lapel",
+    "30": "epaulette",
+    "31": "sleeve",
+    "32": "pocket",
+    "33": "neckline",
+    "34": "buckle",
+    "35": "zipper",
+    "36": "applique",
+    "37": "bead",
+    "38": "bow",
+    "39": "flower",
+    "40": "fringe",
+    "41": "ribbon",
+    "42": "rivet",
+    "43": "ruffle",
+    "44": "sequin",
+    "45": "tassel"
+  },
+  "image_size": [
+    512,
+    864
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "applique": 36,
+    "bag, wallet": 24,
+    "bead": 37,
+    "belt": 19,
+    "bow": 38,
+    "buckle": 34,
+    "cape": 12,
+    "cardigan": 3,
+    "coat": 9,
+    "collar": 28,
+    "dress": 10,
+    "epaulette": 30,
+    "flower": 39,
+    "fringe": 40,
+    "glasses": 13,
+    "glove": 17,
+    "hat": 14,
+    "headband, head covering, hair accessory": 15,
+    "hood": 27,
+    "jacket": 4,
+    "jumpsuit": 11,
+    "lapel": 29,
+    "leg warmer": 20,
+    "neckline": 33,
+    "pants": 6,
+    "pocket": 32,
+    "ribbon": 41,
+    "rivet": 42,
+    "ruffle": 43,
+    "scarf": 25,
+    "sequin": 44,
+    "shirt, blouse": 0,
+    "shoe": 23,
+    "shorts": 7,
+    "skirt": 8,
+    "sleeve": 31,
+    "sock": 22,
+    "sweater": 2,
+    "tassel": 45,
+    "tie": 16,
+    "tights, stockings": 21,
+    "top, t-shirt, sweatshirt": 1,
+    "umbrella": 26,
+    "vest": 5,
+    "watch": 18,
+    "zipper": 35
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "yolos",
+  "num_attention_heads": 6,
+  "num_channels": 3,
+  "num_detection_tokens": 100,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "use_mid_position_embeddings": true
+}

preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "YolosFeatureExtractor",
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "max_size": 1333,
+  "size": 512
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5f4cc272f8f32b2f25b129f9ce7df4756cb030d5fbd234c790b6a9eef962a1
+size 122738781